Home | Business News | Browse by Publication | I | International Journal of Market Research

Developments in outputs from the 2001 Census.

Article Excerpt
The 2001 Census is starting to provide market researchers with updated information on the size and structure of the UK population. The objective of this paper is to identify the most important methodological changes and developments in the 2001 package that will be relevant when using results from this unique source. Section 2 of the paper gives an overview of the Census operation and goes on to discuss the top-line results and why they have led to revision of the mid-year estimates series from 1982 to 2000. Section 3 highlights a number of innovations in Census outputs and discusses their implications for users of the data.

1 Introduction

The Census of Population is arguably the information bedrock that underpins all survey research undertaken in this country. While this statement could be made for every census, the 2001 Census goes a long way further than its predecessors in terms of access to high-quality demographic data. For 2001, the Census Offices 'broke the mould' and introduced a number of major innovations--including new questions in a new form design, a new data-collection procedure, automatic data capture and coding, and a revolutionary new strategy for disseminating the results.

These innovations--particularly the ones that impact on census outputs--will have significant implications for users. Users will need to understand both the obvious and subtle changes in order to obtain maximum benefit from the new results. In particular, market and social researchers who use the Census to plan, sample or control population surveys will need to review and adjust their procedures in an appropriate way to reflect the new data, the bulk of which is being released in the first half of 2003.

The main objective of this paper is to identify and explain briefly the key innovations that will impact on the ways that Census data is used in market research. For a more complete description of the Census operation, or for more details about the innovations outlined here, the reader is encouraged to obtain further information either online--see ONS (2001) or MRS (2001)--or from Census guides such as Dugmore and Moy (2003). The reader may also find independent assessments of various aspects of the Census in reports by the House of Commons Treasury Committee (2002) and the National Audit Office (2002).

This paper contains two main sections. Section 2 gives a brief overview of the 2001 Census operation, highlights the early results released in September 2002, and summarises the knock-on effect of these results on UK population estimates and projections. It provides some background for those interested in the data-collection process and in population data more deeply. Section 3 identifies a number of key innovations impacting on census outputs and discusses their implications, and therefore will be of wider relevance to market researchers.

2 Overview of the 2001 Census

Data-collection method

Planning for 2001 started early in the inter-Census decade, soon after the completion of output processing from the 1991 Census. The 1991 operation had generally gone well; however, certain sections of the population, such as young men, had proved hard to enumerate--both in the main fieldwork and in the subsequent data quality survey. The outcome was that the national total for Great Britain was judged to undercount by 1.2 million individuals, with the missing elements distributed unevenly across the population. Adjustment factors were issued for improving estimates based upon the Census; however, the Census outputs were not adjusted, and users had to make their own decisions on whether and how to compensate for the coverage issue.

Given the 1991 experience, the Census Offices wished to develop a methodology that improved the enumeration of 'hard to find' groups, and targeted areas where response would be low, such as traditionally difficult inner-city areas. At the same time, they were keen to estimate the element missed by the Census and to generate results reflecting the entire population.

The data-capture methodology selected for 2001 was to use enumerators to deliver Census forms, for self-completion and return by each household. Enumerators were then used to follow up non-respondents and obtain completed forms. The Census form was redesigned to make it easier for self-completion, replacing the previous 'matrix-style' layout with a separate section for each member of the household. At the same time the new form was designed for optical scanning, image recognition and automated data entry. The new methodology and design were tested in 1997 and were shown to provide acceptable results.

Census fieldwork

As a result of introducing the postback procedure, the number of enumerators required to carry out the Census could be significantly reduced. The 2001 Census was conducted by 70,00 field staff, compared with 105,000 in 1991. To help enumerators with their task of finding all households and placing forms, they were given computer-generated maps and address lists for their areas. This information needed to be very accurate; therefore the maps were generated using high-resolution digitised boundaries of enumeration districts (Eds), while the addresses within Eds were extracted using one-metre grid references from the Ordnance Survey.

Forms were delivered to all households during the three weeks before Census day, which was Sunday, 29 April. During the run-up to Census day, a publicity campaign was undertaken to generate awareness and request co-operation from the public. The...

View this article FREE - Now for a Limited Time, try Goliath Business News
Free for 3 Days!